Related papers: Single-View and Multi-View Depth Fusion
Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions and occlusions.…
There has been a recent surge of interest in learning to perceive depth from monocular videos in an unsupervised fashion. A key challenge in this field is achieving robust and accurate depth estimation in challenging scenarios, particularly…
Depth estimation and 3D object detection are critical for scene understanding but remain challenging to perform with a single image due to the loss of 3D information during image capture. Recent models using deep neural networks have…
Learning-based Multi-View Stereo (MVS) methods aim to predict depth maps for a sequence of calibrated images to recover dense point clouds. However, existing MVS methods often struggle with challenging regions, such as textureless regions…
Monocular depth estimation is vital for scene understanding and downstream tasks. We focus on the supervised setup, in which ground-truth depth is available only at training time. Based on knowledge about the high regularity of real 3D…
High-fidelity 3D scene reconstruction from monocular videos continues to be challenging, especially for complete and fine-grained geometry reconstruction. The previous 3D reconstruction approaches with neural implicit representations have…
Depth from a monocular video can enable billions of devices and robots with a single camera to see the world in 3D. In this paper, we present an approach with a differentiable flow-to-depth layer for video depth estimation. The model…
Existing monocular depth estimation methods have achieved excellent robustness in diverse scenes, but they can only retrieve affine-invariant depth, up to an unknown scale and shift. However, in some video-based scenarios such as video…
Multi-modal depth estimation is one of the key challenges for endowing autonomous machines with robust robotic perception capabilities. There have been outstanding advances in the development of uni-modal depth estimation techniques based…
Depth completion, aiming to predict dense depth maps from sparse depth measurements, plays a crucial role in many computer vision related applications. Deep learning approaches have demonstrated overwhelming success in this task. However,…
Self-supervised monocular depth estimation (MDE) has gained popularity for obtaining depth predictions directly from videos. However, these methods often produce scale invariant results, unless additional training signals are provided.…
The success of monocular depth estimation relies on large and diverse training sets. Due to the challenges associated with acquiring dense ground-truth depth across different environments at scale, a number of datasets with distinct…
Multi-task approaches to joint depth and segmentation prediction are well-studied for monocular images. Yet, predictions from a single-view are inherently limited, while multiple views are available in many robotics applications. On the…
Self-supervised monocular depth estimation networks are trained to predict scene depth using nearby frames as a supervision signal during training. However, for many applications, sequence information in the form of video frames is also…
A key contributor to recent progress in 3D detection from single images is monocular depth estimation. Existing methods focus on how to leverage depth explicitly, by generating pseudo-pointclouds or providing attention cues for image…
Depth estimation is usually ill-posed and ambiguous for monocular camera-based 3D multi-person pose estimation. Since LiDAR can capture accurate depth information in long-range scenes, it can benefit both the global localization of…
Self-supervised monocular depth estimation has gathered notable interest since it can liberate training from dependency on depth annotations. In monocular video training case, recent methods only conduct view synthesis between existing…
This paper reports a new continuous 3D loss function for learning depth from monocular images. The dense depth prediction from a monocular image is supervised using sparse LIDAR points, which enables us to leverage available open source…
Depth estimation is a challenging task of 3D reconstruction to enhance the accuracy sensing of environment awareness. This work brings a new solution with a set of improvements, which increase the quantitative and qualitative understanding…
Multi-view depth estimation has achieved impressive performance over various benchmarks. However, almost all current multi-view systems rely on given ideal camera poses, which are unavailable in many real-world scenarios, such as autonomous…